gradient
ko · counterpart 그래디언트
The slope of a function in many directions at once. For a function f(x, y, z, ...), the gradient is the vector of partial derivatives — it points in the direction of steepest ascent. In machine learning, this vector tells the optimizer which way to step the parameters to reduce loss.
invented
1847 · Augustin-Louis Cauchy · Paris
Cauchy's *Méthode générale pour la résolution des systèmes d'équations simultanées* introduced what we now call gradient descent — 'follow the steepest slope downhill, repeat'. He was solving systems of nonlinear equations, not training neural networks; the algorithm has not changed.
related
used on · 3